fix

app.py

@@ -65,9 +65,12 @@ def process_audio(audio, text, chat_history):
     generation_args = {
         "max_new_tokens": 4096,
         "streamer": streamer,
+        "eos_token_id":151645, 
+        "pad_token_id":151643,
         **inputs
     }
     # Start a separate thread for model generation to allow streaming output
+    chat_history.append({"role": "assistant", "content": ""})
     thread = Thread(
         target=model.generate,
         kwargs=generation_args,